Create app.py

app.py

@@ -0,0 +1,19 @@
+import gradio as gr
+from diffusers import AudioLDMControlNetPipeline, ControlNetModel
+from pretty_midi import PrettyMIDI
+import torch
+
+if torch.cuda.is_available():
+    device = "cuda"
+    torch_dtype = torch.float16
+else:
+    device = "cpu"
+    torch_dtype = torch.float32
+
+midi = PrettyMIDI("test.mid")
+
+controlnet = ControlNetModel.from_pretrained("lauraibnz/midi-audioldm", torch_dtype=torch_dtype)
+pipe = AudioLDMControlNetPipeline.from_pretrained("cvssp/audioldm-m-full", controlnet=controlnet, torch_dtype=torch_dtype)
+pipe = pipe.to(device)
+
+audio = pipe("techno", audio_length_in_s=10, num_inference_steps=20, midi=midi, controlnet_conditioning_scale=1.0)